Google Research Open-Sources Harness² for Recursive Agent Harness Optimization
11/11/2026 — 11/11, 23:18·1 sources (all)·1 reports (all)
Key takeaways
- Google Research has open-sourced Harness², an automated optimization framework for agent harnesses. The framework optimizes eight editable c…
Background & analysis
On 2026-11-11, a report on Juejin stated that Google Research has open-sourced Harness², an automated framework for optimizing an Agent Harness. According to the report, Harness² does not train the model or change model weights. Instead, it persistently optimizes eight editable components: the prompt, guardrails, memory, tool descriptions, sub-Agents, skills, scripts, and plugins. No further details were given in the source material about how the framework was published, and no subsequent reports have appeared to date.
AI-generated from 1 reports · updated 2 days ago
- Heat index
- 26
- All sources
- 1
- All reports
- 1
- First seen
- 2 days ago
Reports on this story headlines open the original
According to Juejin, Google Research has open-sourced Harness², an automated optimization framework for AI agents. Rather than modifying model weights, it optimizes eight editable components including prompts, guardrails, memory, tool descriptions, sub-agents, skills, scripts, and plugins.
掘金AI score 82
Other stories people are talking about
- Heat index 86NewGoogle Cloud Launches Kubernetes Cost Control Solution for Idle AI Agents1 sources
- Heat index 94NewGoogle Engineer Compiles Agent Engineering Practices into Reusable Skill Library1 sources
- Heat index 2236Nvidia stock plunges after Jensen Huang resigns, with retail investors buying the dip35 sources
- Heat index 1463RisingGoogle Opens Gemini 4 Hydrogen to All Users as High-Speed Model21 sources
- Heat index 1429SurgeJensen Huang exits as NVIDIA CEO, leadership vacuum lingers16 sources
How is heat calculated?About the methodHide
Heat counts how many independent sources covered a story in the last 48 hours: one source counts once no matter how many posts it published, decaying with a 24-hour half-life. What ranks first is what many people are talking about.
This page aggregates public feeds. Headlines and summaries are machine-organized and remain the property of the original authors; verify important facts at the source. If you believe a headline or summary infringes your rights, email the contact address in the footer with the page URL and basis of your claim, and we will remove or replace it after review.
- Surge
- Discussion rising fast
- New
- First report within 6 hours
- Rising
- Still gathering discussion